接近红外光谱的机器学习方法用于预测甜的感觉特征
Judith Ssali Nantongo1, Edwin Serunkuma1, Gabriela Burgos2
1International Potato Center, Ntinda II Road, Plot 47, P.O Box 22274 Kampala, Uganda.
概括
近红外 (NIR) 光谱可以估计甜的感觉特征. 线性模型,如线性支向量机 (L-SVM) 和主要成分回归 (PCR) 显示出这些特征的最佳预测准确性.
科学领域:
- 农业科学 农业科学
- 食品科学 食品科学 食品科学
- 频谱学是一种光谱学.
背景情况:
- 感官和质地特征对于甜的接受度至关重要,影响粮食安全和营养.
- 近红外 (NIR) 光谱学提供了估计这些特征的潜力,由于直接的光谱反应.
- 传统的方法,如部分最小平方 (PLS) 回归,已被用于模拟NIR光谱数据的感觉特征.
研究的目的:
- 用NIR光谱来比较各种机器学习方法的性能,用于使用NIR光谱对甜的感觉特征进行定量预测.
- 识别先进的技术,可以提高新样本的建模精度,并捕捉非线性关系.
主要方法:
- 使用机器学习算法开发和比较27种感官特征的定量预测模型.
- 评估线性方法 (线性支向量机 - L-SVM,主要成分回归 - PCR,PLS) 和非线性方法 (基于辐射的SVM - NL-SVM).
- 评估基于树的方法 (极端梯度提升 - XGBoost,随机森林 - RF) 和弹性净线性回归 (ENR),有或没有有效波长选择 (iPLS) 和SNV预处理.
主要成果:
- 线性方法 (L-SVM,PCR,PLS) 通常优于其他统计方法,表现出更高的R2平均值.
- 与PLS (平均0.32) 和NL-SVM (平均0.30) 相比,L-SVM和PCR模型的整体R2略高 (平均0.33).
- 色强度是最好的预测特征 (R2 = 0.87-0.89),而ENR,XGBoost和RF表现不那么有效 (R2较低和RMSE较高),可能是由于样本大小.
结论:
- 线性模型,特别是L-SVM和PCR,在使用NIR光谱学预测甜的感觉特征方面是有效的.
- 虽然有效的波长选择和预处理方法可以提高模型性能,但线性方法显示出强大的预测能力.
- 用更大的样本大小进行进一步的研究可能会提高基于树的和ENR模型的性能,用于基于NIR的感觉特征预测.
更多相关视频
06:50O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
Published on: November 8, 2019
6.6K
11:37RGB and Spectral Root Imaging for Plant Phenotyping and Physiological Research: Experimental Setup and Imaging Protocols
Published on: August 8, 2017
16.2K
相关概念视频
Key Elements for Plant Nutrition
18.7K
Like all living organisms, plants require organic and inorganic nutrients to survive, reproduce, grow and maintain homeostasis. To identify nutrients that are essential for plant functioning, researchers have leveraged a technique called hydroponics. In hydroponic culture systems, plants are grown—without soil—in water-based solutions containing nutrients. At least 17 nutrients have been identified as essential elements required by plants. Plants acquire these elements from the...
18.7K
Light Acquisition
8.5K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.5K
